© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45697
    Prev
    Next
    INDEX
    Explanations

    visual attention and prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osu
    -0.09
    æĬĺèħ¾
    -0.08
     administrations
    -0.08
     deaths
    -0.07
    utan
    -0.07
    ç½ijç«Ļ导èĪª
    -0.07
    æĸĩåĮĸèīºæľ¯
    -0.07
    ÏĢαν
    -0.07
    åī²
    -0.07
     Insp
    -0.07
    POSITIVE LOGITS
     cues
    0.10
    çŁ¥è§ī
    0.10
     cognition
    0.09
     cue
    0.09
    æĥħå¢ĥ
    0.08
     ÑģенÑģоÑĢ
    0.08
    æĦŁçŁ¥
    0.08
     neural
    0.08
     gestalt
    0.08
     processing
    0.08
    Activations Density 0.177%

    No Known Activations